fetch

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds useful behavior beyond the annotations: pagination via snapshot and next_offset, unknown HTML completeness and legal dates, and the caution that retrieved text is untrusted data. This gives the agent meaningful handling guidance that readOnlyHint/openWorldHint alone do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very brief and dense, with no filler. Each sentence contributes either reference formats, pagination behavior, or data-quality caveats, and the most important action is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-output-schema fetch tool with four parameters, it covers source reference formats and pagination but omits the return shape beyond snapshot/next_offset and the behavior of length, offset, and as_of_date. It is sufficient for basic invocation but not complete for nuanced use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate for all four parameters. It does document source_ref formats and hints at pagination via next_offset, but length, offset, and as_of_date semantics remain undefined, leaving most parameters ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a distinct action ('Retrieve a supported source and issue evidence') and enumerates accepted reference forms, giving the agent a concrete idea of what this tool targets. It does not explicitly contrast with siblings like search or get_legal_version, so sibling differentiation is absent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The reference-form list and 'Follow evidence: snapshot and next_offset' imply the tool is for paginated retrieval by source reference. However, it never states when to choose fetch over search, get_source_status, or check_evidence, nor does it mention exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.